728x90
1. Prompt Injection
2. Sensitive Information Disclosure
3. Supply Chain
4. Data and Model Poisoning
5. Improper Output handling
6. Improper Output Handling
7. Excessive Agency
7. System Prompt Leakage
8. Vector and Embedding Weaknesses
9. Imsinformation
10. Unbounded Consumption
https://genai.owasp.org/resource/owasp-top-10-for-llm-applications-2025/
OWASP Top 10 for LLM Applications 2025 - OWASP Top 10 for LLM & Generative AI Security
The OWASP Top 10 for Large Language Model Applications started in 2023 as a community-driven effort to highlight and address security issues specific to AI applications. Since then, the technology has continued to spread across industries and applications,
genai.owasp.org
반응형
'IT Tech > Security' 카테고리의 다른 글
| 양자내성암호(PQC, Post-Quantum Cryptography) (0) | 2025.01.03 |
|---|---|
| SW 공급망 보안 가이드라인 (1) | 2025.01.02 |
| Visual Studio Code tennel을 이용한 해킹 공격 (0) | 2024.12.31 |
| 제로트러스트 가이드라인 2.0 (0) | 2024.12.05 |
| 개인정보보호책임자(CPO) 가이드북 (1) | 2024.11.20 |